x-transformers 2.3.11__py3-none-any.whl → 2.3.12__py3-none-any.whl

x_transformers/x_transformers.py

@@ -1981,6 +1981,7 @@ class AttentionLayers(Module):
         learned_value_residual_mix = True,   # seeing big improvements when the value residual mix value is learned per token - credit goes to @faresobeid for taking the first step with learned scalar mix, then @Blinkdl for taking it a step further with data dependent. here we will use per token learned
         rel_pos_kwargs: dict = dict(),
         residual_fn_kwargs: dict = dict(),
+        verbose = True,
         **kwargs
     ):
         super().__init__()
@@ -2032,7 +2033,7 @@ class AttentionLayers(Module):
 
         assert rotary_emb_dim <= dim_head, f'rotary emb dim {rotary_emb_dim} must be less than or equal to attention head dimension {dim_head}'
 
-        if rotary_emb_dim < 32:
+        if verbose and rotary_emb_dim < 32:
             logger.warning('when training language model, rotary embedding dimension should be at least 32')
 
         assert not (rotary_xpos and not causal), 'rotary xpos is not compatible with bidirectional attention'

{x_transformers-2.3.11.dist-info → x_transformers-2.3.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: x-transformers
-Version: 2.3.11
+Version: 2.3.12
 Summary: X-Transformers
 Project-URL: Homepage, https://pypi.org/project/x-transformers/
 Project-URL: Repository, https://github.com/lucidrains/x-transformers

{x_transformers-2.3.11.dist-info → x_transformers-2.3.12.dist-info}/RECORD

@@ -8,10 +8,10 @@ x_transformers/entropy_based_tokenizer.py,sha256=F2lO8-v3aLIcVDVNhu7RR-UtRdlmaaY
 x_transformers/multi_input.py,sha256=tCh-fTJDj2ib4SMGtsa-AM8MxKzJAQSwqAXOu3HU2mg,9252
 x_transformers/neo_mlp.py,sha256=XCNnnop9WLarcxap1kGuYc1x8GHvwkZiDRnXOxSl3Po,3452
 x_transformers/nonautoregressive_wrapper.py,sha256=2NU58hYMgn-4Jzg3mie-mXb0XH_dCN7fjlzd3K1rLUY,10510
-x_transformers/x_transformers.py,sha256=Wo5hauzdn4Q9PUVjBqQo-1vCq08BT2jYUDbq3r2a5Go,114061
+x_transformers/x_transformers.py,sha256=ZfOXrZSiy2jlZ8wVmDdMTLW4hAY_qfmPQHW9t2ABxbo,114097
 x_transformers/xl_autoregressive_wrapper.py,sha256=CvZMJ6A6PA-Y_bQAhnORwjJBSl6Vjq2IdW5KTdk8NI8,4195
 x_transformers/xval.py,sha256=7S00kCuab4tWQa-vf-z-XfzADjVj48MoFIr7VSIvttg,8575
-x_transformers-2.3.11.dist-info/METADATA,sha256=cDJW4GNyTXb0gKUm-Z_T8Bk1Jrk8HJU35v6tldG2IJo,89022
-x_transformers-2.3.11.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-x_transformers-2.3.11.dist-info/licenses/LICENSE,sha256=As9u198X-U-vph5noInuUfqsAG2zX_oXPHDmdjwlPPY,1066
-x_transformers-2.3.11.dist-info/RECORD,,
+x_transformers-2.3.12.dist-info/METADATA,sha256=ADkMqVrlqcYcMk8U_9oxqOHc4XRD1NbSfVJsGhy5R8s,89022
+x_transformers-2.3.12.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+x_transformers-2.3.12.dist-info/licenses/LICENSE,sha256=As9u198X-U-vph5noInuUfqsAG2zX_oXPHDmdjwlPPY,1066
+x_transformers-2.3.12.dist-info/RECORD,,